Abstract. In this paper we propose a novel variational technique for the knowledge based segmentation of two dimensional objects. One of the elements of our approach is the use of ...
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
In this paper we address the problem of aligning 3-D data with articulated shapes. This problem resides at the core of many motion tracking methods with applications in human motio...
Guillaume Dewaele, Frederic Devernay, Radu Horaud,...
This paper presents a hybrid 1D motion estimation algorithm which combines pixel-based and region-based approaches that can give depth images from translational video sequences wi...
Life-likeanimatedinterfaceagentsforknowledge-basedlearning environments can provide timely, customized advice to support students’ problem solving. Because of their strong visua...
Stuart G. Towns, Jennifer L. Voerman, Charles B. C...